Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4199 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8767. Min Range: -2.8767
Max Act: 2.8767. Min Act: -0.1700
Data Index: 1734957 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8767. Min Range: -2.8767
Max Act: 2.7015. Min Act: -0.1700
Data Index: 7006534 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8767. Min Range: -2.8767
Max Act: 2.6374. Min Act: -0.1700
Data Index: 142874 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8767. Min Range: -2.8767
Max Act: 2.6374. Min Act: -0.1700
Data Index: 5481091 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8767. Min Range: -2.8767
Max Act: 2.5891. Min Act: -0.1700
Data Index: 800821 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8767. Min Range: -2.8767
Max Act: 2.5891. Min Act: -0.1700
Data Index: 4951367 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8767. Min Range: -2.8767
Max Act: 2.5891. Min Act: -0.1700
Data Index: 3190396 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8767. Min Range: -2.8767
Max Act: 2.5730. Min Act: -0.1700
Data Index: 5507953 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8767. Min Range: -2.8767
Max Act: 2.5730. Min Act: -0.1700
Data Index: 7803487 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8767. Min Range: -2.8767
Max Act: 2.5569. Min Act: -0.1700
Data Index: 1060358 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8767. Min Range: -2.8767
Max Act: 2.5569. Min Act: -0.1700
Data Index: 4175544 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8767. Min Range: -2.8767
Max Act: 2.5569. Min Act: -0.1700
Data Index: 6221435 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8767. Min Range: -2.8767
Max Act: 2.5569. Min Act: -0.1700
Data Index: 6407841 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8767. Min Range: -2.8767
Max Act: 2.5569. Min Act: -0.1700
Data Index: 2342183 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8767. Min Range: -2.8767
Max Act: 2.5730. Min Act: -0.1700
Data Index: 4413262 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8767. Min Range: -2.8767
Max Act: 2.5569. Min Act: -0.1700
Data Index: 4772084 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8767. Min Range: -2.8767
Max Act: 2.5569. Min Act: -0.1700
Data Index: 1264150 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8767. Min Range: -2.8767
Max Act: 2.5569. Min Act: -0.1700
Data Index: 7060278 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8767. Min Range: -2.8767
Max Act: 2.5569. Min Act: -0.1700
Data Index: 898376 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8767. Min Range: -2.8767
Max Act: 2.5569. Min Act: -0.1700
Data Index: 7158201 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19